Yolov3训练教程Keras

欢迎关注的公众号：
不定期发布各类教程、理论笔记、搬运前沿动态。

环境搭建教程在上一篇博客Keras yolov3环境搭建
1、打开文件夹
用 pycharm 打开 keras-yolo3 文件夹打开的文件夹应该是这样的：2、新建voc2007数据集（存放自己的图片及标注信息）
新建的文件夹（ImageSets 文件夹下还有个名为 Main 的小文件夹自己创建吧没截图）如下：

3、将要训练的图片放在 JPEGImages 里面：
labelimg 标注的 xlm 文件放在 Annotations 里面

4、在 VOC2007 里新建一个 py 文件，在此取名 voc.py

VOC中的代码如下：

import os
import random

trainval_percent = 0.2 #测试集占0.2
train_percent = 0.8    #训练集占0.8
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

直接复制以上代码即可，然后运行 voc.py 文件
运行后会在mian 文件夹里会多了四个 txt 文件

5、修改 voc_annotation.py 文件并运行
更改这里的 classes 的数量，你voc2007里标注了哪几种，你就留哪几种就行

比如voc中只标注将 coco_classes.txt 和 voc_classes.txt 中也只留下VOC2007 中所标注的那个类型rson”，那只留下“person”，然后再运行一下就行，运行完成后会多出这几个 txt 文件

6、修改 model_data
将 coco_classes.txt 和 voc_classes.txt 中也只留下VOC2007 中所标注的那个类型比如标注的只有 “person”
那只留下“person”

7、修改 yolo3.cfg
大概在 610、696 和 783 行的位置，把 classes 的数值都改为 1


8、添加官方权重
将 yolo.h5 改名为 yolo_weights.h5

9、新建 logs 文件夹存放训练的权重文件。

10、开始训练
在 keras-yolo3-master 文件夹下新建 一个名为 trainyolo.py 的文件
trainyolo代码如下：

import numpy as np
import tensorflow as tf
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.optimizers import Adam
from keras.callbacks import TensorBoard, ModelCheckpoint, ReduceLROnPlateau, EarlyStopping
from yolo3.model import yolo_body
from yolo3.model import yolo_loss
from keras.backend.tensorflow_backend import set_session
from yolo3.utils import get_random_data

def get_classes(classes_path):
    '''loads the classes'''
    with open(classes_path) as f:
        class_names = f.readlines()
    class_names = [c.strip() for c in class_names]
    return class_names

def get_anchors(anchors_path):
    '''loads the anchors from a file'''
    with open(anchors_path) as f:
        anchors = f.readline()
    anchors = [float(x) for x in anchors.split(',')]
    return np.array(anchors).reshape(-1, 2)

def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
    '''data generator for fit_generator'''
    n = len(annotation_lines)
    i = 0
    while True:
        image_data = []
        box_data = []
        for b in range(batch_size):
            if i==0:
                np.random.shuffle(annotation_lines)
            image, box = get_random_data(annotation_lines[i], input_shape, random=True)
            image_data.append(image)
            box_data.append(box)
            i = (i+1) % n
        image_data = np.array(image_data)
        box_data = np.array(box_data)
        y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
        yield [image_data, *y_true], np.zeros(batch_size)

def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):

    assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
    
    num_layers = len(anchors)//3 
    anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]

    true_boxes = np.array(true_boxes, dtype='float32')
    input_shape = np.array(input_shape, dtype='int32') # 416,416
    boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
    boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
    true_boxes[..., 0:2] = boxes_xy/input_shape[:]
    true_boxes[..., 2:4] = boxes_wh/input_shape[:]

    m = true_boxes.shape[0]
    grid_shapes = [input_shape//{0:32, 1:16, 2:8}[l] for l in range(num_layers)]
    y_true = [np.zeros((m,grid_shapes[l][0],grid_shapes[l][1],len(anchor_mask[l]),5+num_classes),
        dtype='float32') for l in range(num_layers)]
    anchors = np.expand_dims(anchors, 0)
    anchor_maxes = anchors / 2.
    anchor_mins = -anchor_maxes
    valid_mask = boxes_wh[..., 0]>0

    for b in range(m):
        wh = boxes_wh[b, valid_mask[b]]
        if len(wh)==0: continue
        wh = np.expand_dims(wh, -2)
        box_maxes = wh / 2.
        box_mins = -box_maxes

        intersect_mins = np.maximum(box_mins, anchor_mins)
        intersect_maxes = np.minimum(box_maxes, anchor_maxes)
        intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
        intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
        box_area = wh[..., 0] * wh[..., 1]
        anchor_area = anchors[..., 0] * anchors[..., 1]
        iou = intersect_area / (box_area + anchor_area - intersect_area)
        best_anchor = np.argmax(iou, axis=-1)

        for t, n in enumerate(best_anchor):
            for l in range(num_layers):
                if n in anchor_mask[l]:
                    i = np.floor(true_boxes[b,t,0]*grid_shapes[l][1]).astype('int32')
                    j = np.floor(true_boxes[b,t,1]*grid_shapes[l][0]).astype('int32')
                    k = anchor_mask[l].index(n)
                    c = true_boxes[b,t, 4].astype('int32')
                    y_true[l][b, j, i, k, 0:4] = true_boxes[b,t, 0:4]
                    y_true[l][b, j, i, k, 4] = 1
                    y_true[l][b, j, i, k, 5+c] = 1

    return y_true


config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
config.gpu_options.per_process_gpu_memory_fraction = 0.7
config.gpu_options.allow_growth = True
set_session(tf.Session(config=config)) 

if __name__ == "__main__":
    annotation_path = '2007_train.txt'
    classes_path = 'model_data/voc_classes.txt'    
    anchors_path = 'model_data/yolo_anchors.txt'
    weights_path = 'model_data/yolo_weights.h5'
    class_names = get_classes(classes_path)
    anchors = get_anchors(anchors_path)
    num_classes = len(class_names)
    num_anchors = len(anchors)
    log_dir = 'logs/'
    input_shape = (416,416)

    K.clear_session()

    image_input = Input(shape=(None, None, 3))
    h, w = input_shape

    print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
    model_body = yolo_body(image_input, num_anchors//3, num_classes)
    
    print('Load weights {}.'.format(weights_path))
    model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
    
    y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
        num_anchors//3, num_classes+5)) for l in range(3)]

    loss_input = [*model_body.output, *y_true]
    model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
        arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(loss_input)

    model = Model([model_body.input, *y_true], model_loss)

    freeze_layers = 249
    for i in range(freeze_layers): model_body.layers[i].trainable = False
    print('Freeze the first {} layers of total {} layers.'.format(freeze_layers, len(model_body.layers)))

    logging = TensorBoard(log_dir=log_dir)
    checkpoint = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
        monitor='val_loss', save_weights_only=True, save_best_only=False, period=2)
    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2, verbose=1)
    early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=6, verbose=1)

    val_split = 0.2
    with open(annotation_path) as f:
        lines = f.readlines()
    np.random.seed(10101)
    np.random.shuffle(lines)
    np.random.seed(None)
    num_val = int(len(lines)*val_split)
    num_train = len(lines) - num_val
    
    if True:
        model.compile(optimizer=Adam(lr=1e-3), loss={
            'yolo_loss': lambda y_true, y_pred: y_pred})

        batch_size = 1
        print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
        model.fit_generator(data_generator(lines[:num_train], batch_size, input_shape, anchors, num_classes),
                steps_per_epoch=max(1, num_train//batch_size),
                validation_data=data_generator(lines[num_train:], batch_size, input_shape, anchors, num_classes),
                validation_steps=max(1, num_val//batch_size),
                epochs=50,
                initial_epoch=0,
                callbacks=[logging, checkpoint])
        model.save_weights(log_dir + 'trained_weights_stage_1.h5')

    for i in range(freeze_layers): model_body.layers[i].trainable = True

    if True:
        model.compile(optimizer=Adam(lr=1e-4), loss={
            'yolo_loss': lambda y_true, y_pred: y_pred})

        batch_size = 1
        print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
        model.fit_generator(data_generator(lines[:num_train], batch_size, input_shape, anchors, num_classes),
                steps_per_epoch=max(1, num_train//batch_size),
                validation_data=data_generator(lines[num_train:], batch_size, input_shape, anchors, num_classes),
                validation_steps=max(1, num_val//batch_size),
                epochs=100,
                initial_epoch=50,
                callbacks=[logging, checkpoint])
        model.save_weights(log_dir + 'last1.h5')

11、然后运行trainyolo.py 的代码
开始训练了。
当出现下图所示，训练完成

训练好的权重都放在 logs 文件夹下的 000 文件夹里：

这两个权重文件都可以用一样的

然后和之前一样加载权重，识别照片就可以了！